Back

Automating the Construction of Contextualized Biomedical Knowledge Graphs for Scientific Inference

Zheng, Y.; Liu, W.; Zeng, B.; Feng, Y.; Du, X.; Zhou, L.; Li, Y.

2026-01-14 bioinformatics
10.64898/2026.01.14.699420 bioRxiv
Show abstract

Biomedical interactions are inherently dynamic, often shifting or even reversing under specific physiological states. However, existing extraction methods simplify these complex mechanisms into context-agnostic binary associations, resulting in semantic loss and contradictory evidence. Here, we present AutoBioKG, an end-to-end framework that constructs context-aware knowledge graphs by leveraging composite triplets to encode environmental conditions and entity attributes alongside core relationships. Powered by a self-evolving open information extraction model trained solely on our curated BioOpenIE dataset, the framework refines its generalization capabilities. Notably, AutoBioKG surpasses state-of-the-art large language models in zero-shot settings, achieving F1 score improvements ranging from 18.5% to 20.7% across three benchmarks (DDI, ChemProt, and BioRED). Furthermore, AutoBioKG-derived graphs significantly outperform existing approaches in the BioASQ biomedical question-answering task, particularly for complex queries requiring fine-grained contextual information. AutoBioKG offers a scalable and accessible solution for transforming unstructured literature into actionable biomedical knowledge.

Matching journals

The top 7 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.